This book is a collection of papers that are representative of a growing body of work in computational auditory scene analysis. It covers the work being done to integrate speech and nonspeech understanding in computer systems by representing some advanced work on computers understanding speech.

Humans and other mammals have the ability to selectively attend to sound from a particular source, even when it is mixed with other sounds. Computers also need to be able to decide which parts of a mixed acoustic signal are relevant to a particular purpose. This book covers the integration of speech and nonspeech understanding in computer systems.